scholarly journals Specialising neural network potentials for accurate properties and application to the mechanical response of titanium

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Tongqi Wen ◽  
Rui Wang ◽  
Lingyu Zhu ◽  
Linfeng Zhang ◽  
Han Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Mechanical Response ◽  
Interatomic Potential ◽  
Dislocation Core ◽  
General Purpose ◽  
Direct Access ◽  
Interatomic Potentials ◽  
Atomistic Modelling ◽  
Complex Phenomena

AbstractLarge scale atomistic simulations provide direct access to important materials phenomena not easily accessible to experiments or quantum mechanics-based calculation approaches. Accurate and efficient interatomic potentials are the key enabler, but their development remains a challenge for complex materials and/or complex phenomena. Machine learning potentials, such as the Deep Potential (DP) approach, provide robust means to produce general purpose interatomic potentials. Here, we provide a methodology for specialising machine learning potentials for high fidelity simulations of complex phenomena, where general potentials do not suffice. As an example, we specialise a general purpose DP method to describe the mechanical response of two allotropes of titanium (in addition to other defect, thermodynamic and structural properties). The resulting DP correctly captures the structures, energies, elastic constants and γ-lines of Ti in both the HCP and BCC structures, as well as properties such as dislocation core structures, vacancy formation energies, phase transition temperatures, and thermal expansion. The DP thus enables direct atomistic modelling of plastic and fracture behaviour of Ti. The approach to specialising DP interatomic potential, DPspecX, for accurate reproduction of properties of interest “X”, is general and extensible to other systems and properties.

scholarly journals Development of a physically-informed neural network interatomic potential for tantalum

2021 ◽  
Author(s):  
Yi-Shen Lin ◽  
G. Purja Pun ◽  
Yuri Mishin
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Interatomic Potential ◽  
Dislocation Core ◽  
General Purpose ◽  
Reference Database ◽  
Interatomic Potentials ◽  
Extended Defects ◽  
Bcc Metals ◽  
Peierls Barrier

Abstract Large-scale atomistic simulations of materials heavily rely on interatomic potentials, which predict the system energy and atomic forces. One of the recent developments in the field is constructing interatomic potentials by machine-learning (ML) methods. ML potentials predict the energy and forces by numerical interpolation using a large reference database generated by quantum-mechanical calculations. While high accuracy of interpolation can be achieved, extrapolation to unknown atomic environments is unpredictable. The recently proposed physically-informed neural network (PINN) model significantly improves the transferability by combining a neural network regression with a physics-based bond-order interatomic potential. Here, we demonstrate that general-purpose PINN potentials can be developed for body-centered cubic (BCC) metals. The proposed PINN potential for tantalum reproduces the reference energies within 2.8 meV/atom. It accurately predicts a broad spectrum of physical properties of Ta, including (but not limited to) lattice dynamics, thermal expansion, energies of point and extended defects, the dislocation core structure and the Peierls barrier, the melting temperature, the structure of liquid Ta, and the liquid surface tension. The potential enables large-scale simulations of physical and mechanical behavior of Ta with nearly first-principles accuracy while being orders of magnitude faster. This approach can be readily extended to other BCC metals.

scholarly journals Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Yury Lysogorskiy ◽  
Cas van der Oord ◽  
Anton Bochkarev ◽  
Sarath Menon ◽  
Matteo Rinaldi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cluster Expansion ◽  
Large Scale ◽  
Pareto Front ◽  
General Purpose ◽  
Basis Functions ◽  
Atomic Energy ◽  
Atomistic Simulations ◽  
Interatomic Potentials ◽  
Atomic Cluster

AbstractThe atomic cluster expansion is a general polynomial expansion of the atomic energy in multi-atom basis functions. Here we implement the atomic cluster expansion in the performant C++ code that is suitable for use in large-scale atomistic simulations. We briefly review the atomic cluster expansion and give detailed expressions for energies and forces as well as efficient algorithms for their evaluation. We demonstrate that the atomic cluster expansion as implemented in shifts a previously established Pareto front for machine learning interatomic potentials toward faster and more accurate calculations. Moreover, general purpose parameterizations are presented for copper and silicon and evaluated in detail. We show that the Cu and Si potentials significantly improve on the best available potentials for highly accurate large-scale atomistic simulations.

scholarly journals Mechanism of amorphous phase stabilization in ultrathin films of monoatomic phase change material

Nanoscale ◽  
2021 ◽  
Author(s):  
Daniele Dragoni ◽  
Jörg Behler ◽  
Marco Bernasconi
Keyword(s):  
Machine Learning ◽  
Phase Change ◽  
Ultrathin Films ◽  
Large Scale ◽  
Interatomic Potential ◽  
Atomistic Simulations ◽  
Machine Learning Method ◽  
Learning Method ◽  
Phase Stabilization ◽  
Change Material

Large scale atomistic simulations with an interatomic potential generated by a machine learning method have been exploited to study the crystallization of Sb in ultrathin films.

MARTT: Automatic Markup of Taxonomic Descriptions with XML

2013 ◽  
Author(s):  
Hong Cui
Keyword(s):  
Machine Learning ◽  
Information Content ◽  
Large Scale ◽  
Learning Algorithms ◽  
General Purpose ◽  
Machine Learning Algorithms ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Taxonomic Descriptions ◽  
Efficient Machine

Despite the sub-language nature of taxonomic descriptions of animals and plants, researchers have warned about the existence of large variations among different description collections in terms of information content and its representation. These variations impose a serious threat to the development of automatic tools to structure large volumes of text-based descriptions. This paper presents a general approach to mark up different collections of taxonomic descriptions with XML, using two large-scale floras as examples. The markup system, MARTT, is based on machine learning methods and enhanced by machine learned domain rules and conventions. Experiments show that our simple and efficient machine learning algorithms outperform significantly general purpose algorithms and that rules learned from one flora can be used when marking up a second flora and help to improve the markup performance, especially for elements that have sparse training examples.Malgré la nature de sous-langage des descriptions taxinomiques des animaux et des plantes, les chercheurs reconnaissent l’existence de vastes variations parmi différentes collections de descriptions, en termes de contenu informationnel et de leur représentation. Ces variations présentent une menace sérieuse pour le développement d’outils automatiques pour la structuration de larges… 

Empirical Interatomic Potentials for L1O Tial and B2 Nial

1990 ◽  
Vol 213 ◽  
Author(s):  
Satish I. Rao ◽  
C. Woodward ◽  
T.A. Parthasarathy
Keyword(s):  
Interatomic Potential ◽  
Dislocation Core ◽  
Interatomic Potentials ◽  
Electronic Effects ◽  
Bulk Properties ◽  
Embedded Atom ◽  
Fitting Procedure ◽  
Planar Fault ◽  
Potential Methods ◽  
Semi Empirical

ABSTRACTRecent studies have suggested a particular relationship between the degree of covalent bonding in TiAl and the mobility of dislocation[1,2]. Ultimately such electronic effects In ordered compounds must dictate the dislocation core structures and at the same time the dislocation mobility within a given compound. However, direct modelling of line defects Is beyond the capability of todays electronic structure techniques. Alternatively, significant steps toward extending our understanding of the flow behaviour of structural intermetallics may come through general application of empirical interatomic potential methods for calculating the structure and mobility of defects. Toward this end, we have constructed semi-empirical interatomic potentials within the embedded atom formalism for L1O and B2 type structures. These potentials have been determined by fitting to known bulk structural and elastic properties of TIAl and NiAl, using least squares procedures. Simple expressions that relate the parameters of the potentials to the bulk properties are used in the fitting procedure. Calculations of dislocation core structures and planar fault energies using these potentials are considered. The differences between the optimized bulk properties predicted from the potentials and the values for these properties are discussed in terms of non-spherical nature of the electron density distribution. Empirical methods which incorporate these effects into interatomic potentials are briefly discussed.

Interatomic Potentials for Atomistic Simulations

MRS Bulletin ◽  
1996 ◽  
Vol 21 (2) ◽  
pp. 17-19 ◽  
Author(s):  
Arthur F. Voter
Keyword(s):  
Atomistic Simulation ◽  
Large Scale ◽  
Materials Science ◽  
Interatomic Potential ◽  
Computer Time ◽  
Atomistic Simulations ◽  
Interatomic Potentials ◽  
Materials Research ◽  
Recent Developments ◽  
Time Required

Atomistic simulations are playing an increasingly prominent role in materials science. From relatively conventional studies of point and planar defects to large-scale simulations of fracture and machining, atomistic simulations offer a microscopic view of the physics that cannot be obtained from experiment. Predictions resulting from this atomic-level understanding are proving increasingly accurate and useful. Consequently, the field of atomistic simulation is gaining ground as an indispensable partner in materials research, a trend that can only continue. Each year, computers gain roughly a factor of two in speed. With the same effort one can then simulate a system with twice as many atoms or integrate a molecular-dynamics trajectory for twice as long. Perhaps even more important, however, are the theoretical advances occurring in the description of the atomic interactions, the so-called “interatomic potential” function.The interatomic potential underpins any atomistic simulation. The accuracy of the potential dictates the quality of the simulation results, and its functional complexity determines the amount of computer time required. Recent developments that fit more physics into a compact potential form are increasing the accuracy available per simulation dollar.This issue of MRS Bulletin offers an introductory survey of interatomic potentials in use today, as well as the types of problems to which they can be applied. This is by no means a comprehensive review. It would be impractical here to attempt to present all the potentials that have been developed in recent years. Rather, this collection of articles focuses on a few important forms of potential spanning the major classes of materials bonding: covalent, metallic, and ionic.

scholarly journals EQUILIBRIUM MOLECULAR DYNAMICS CALCULATIONS OF THERMAL CONDUCTIVITY: A “HOW-TO” FOR THE BEGINNERS

2020 ◽  
Vol 9 (1) ◽  
pp. 11-25
Author(s):  
Jude S. Alexander ◽  
Christopher Maxwell ◽  
Jeremy Pencer ◽  
Mouna Saoudi
Keyword(s):  
Thermal Conductivity ◽  
Molecular Dynamics ◽  
Large Scale ◽  
Interatomic Potential ◽  
Negative Impact ◽  
Significant Risk ◽  
Nonequilibrium Molecular Dynamics ◽  
Atomistic Modelling ◽  
Dynamics Simulations

The ready availability of codes such as LAMMPS (Large-scale Atomic/Molecular Massively Parallel Simulator) for molecular dynamics simulations has opened up the realm of atomistic modelling to novice code users with an interest in computational materials modelling but who lack the appropriate theoretical or computational background. As such, there is significant risk of the “user effect” having a negative impact on the quality of results obtained using such codes. Here, we present a “how-to” procedure for equilibrium molecular dynamics-based nuclear fuel thermal conductivity calculations using the Green–Kubo method with an interatomic potential developed by Cooper et al. [ 1 ]. The various steps of the simulation are identified and explained, along with criteria to assess the quality of the intermediate and final results, discussion of some problems that can arise during a simulation, and some inherent limitations of the method. Calculated thermal conductivities for UO2 and ThO2 will be compared with the available experimental data and also with similar thermal conductivity calculations using nonequilibrium molecular dynamics, reported in the open literature.

scholarly journals Machine Learning Based Prediction of Nanoscale Ice Adhesion on Rough Surfaces

Coatings ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 33
Author(s):  
Simen Ringdahl ◽  
Senbo Xiao ◽  
Jianying He ◽  
Zhiliang Zhang
Keyword(s):  
Machine Learning ◽  
Adhesion Strength ◽  
Liquid Layer ◽  
Interatomic Potential ◽  
Rough Surfaces ◽  
Md Simulations ◽  
Support Vector ◽  
Interatomic Potentials ◽  
Quasi Liquid Layer ◽  
Ice Adhesion

It is widely recognized that surface roughness plays an important role in ice adhesion strength, although the correlation between the two is far from understood. In this paper, two approaches, molecular dynamics (MD) simulations and machine learning (ML), were utilized to study the nanoscale intrinsic ice adhesion strength on rough surfaces. A systematic algorithm for making random rough surfaces was developed and the surfaces were tested for their ice adhesion strength, with varying interatomic potentials. Using MD simulations, the intrinsic ice adhesion strength was found to be significantly lower on rougher surfaces, which was attributed to the lubricating effect of a thin quasi-liquid layer. An increase in the substrate–ice interatomic potential increased the thickness of the quasi-liquid layer on rough surfaces. Two different ML algorithms, regression and classification, were trained using the results from the MD simulations, with support vector machines (SVM) emerging as the best for classifying. The ML approach showed an encouraging prediction accuracy, and for the first time shed light on using ML for anti-icing surface design. The findings provide a better understanding of the role of nanoscale roughness in intrinsic ice adhesion and suggest that ML can be a powerful tool in finding materials with a low ice adhesion strength.

scholarly journals Machine Learning a General-Purpose Interatomic Potential for Silicon

2018 ◽  
Vol 8 (4) ◽  
Author(s):  
Albert P. Bartók ◽  
James Kermode ◽  
Noam Bernstein ◽  
Gábor Csányi
Keyword(s):  
Machine Learning ◽  
Interatomic Potential ◽  
General Purpose
Sign in / Sign up

Export Citation Format

Share Document